Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jacebenson/jsnnpx agentmods add skills/jacebenson/jsn/verifyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jacebenson/jsn/verify)<a href="https://agentmods.dev/skills/jacebenson/jsn/verify"><img src="https://agentmods.dev/badge/skills/jacebenson/jsn/verify/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jacebenson/jsn/verify"><img src="https://agentmods.dev/badge/skills/jacebenson/jsn/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.01173 |
| Opus 5.5 | $0.00015 | $0.00469 |
| Sonnet 5.5 | $0.00007 | $0.00235 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify JSN
This project-local skill is the JSN CLI driver for OpenCode. It follows the pstack-claude verification shape without copying the Cursor plugin. The OpenCode-compatible pstack skills are installed through the documented shared Agent Skills path at ~/.agents/skills/, while this repo-owned skill lives at .agents/skills/verify/. Run it from the repository root.
Launch
JSN is a short-lived Node CLI. There is no server to keep alive and no build step.
npm install
node bin/jsn.js --version
For a global-style executable without publishing anything:
npm link
jsn --version
Use node bin/jsn.js in evidence so the checkout under test is unambiguous. The package requires Node >=22.5.0.
Doctor
Run the read-only doctor before any instance-backed drive:
node .agents/skills/verify/scripts/verify-jsn.mjs doctor --profile pdi --allow-unauthenticated
The doctor proves the repository binary, package version, selected profile name, configured instance hostname, auth method, and authentication state. It prints no usernames, tokens, cookies, passwords, or credential contents. --allow-unauthenticated is only for the local-fixture lane. Without it, an unauthenticated or stale profile fails and must not be driven.
The last verified pdi doctor run found an authenticated, verified profile for dev354702.service-now.com. It is not marked read-only, so use it only for explicitly read-only commands in this kitchen. Do not refresh credentials, log in, mutate records, or use mutation-capable commands unless a disposable profile is separately established and the mutation has an explicit approval.
Runtime references only:
- Config file:
~/.config/servicenow/config.json, or theXDG_CONFIG_HOMEequivalent. - Profile name:
pdiis the known local profile. Confirm it withjsn auth status --json. - Credential source: the OS keyring or the configured auth backend. Never copy it into this repository.
- Optional environment controls used by tests:
JSN_NO_VERSION_CHECK=1,JSN_NO_SKILL_CHECK=1.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 108 lines · 37 tokens per session scan A 5f264d07d130
verify is a skill published in the GitHub repository jacebenson/jsn (12 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,173 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
Other skills, from other repositories
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
winapp-sandbox
Run, debug, and UI-automate a Windows app in a persistent Windows Sandbox rather than the user's desktop. Use for disposable app testing, guest diagnostics, file transfer, and app or whole-desktop evidence. Builds remain on the host; connection and reconnect can briefly take focus.
developing-openrig
Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…
dd-triage-flaky-test
Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.
dd-unblock-pr
Load when investigating a failing PR CI pipeline or checking PR health. Attributes each CI failure as flaky, infra, or regression, proposes a targeted action, and reports code coverage.
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.